NVIDIA
Explore Models Blueprints GPUs
Terms of Use

|

Privacy Policy

|

Manage My Privacy

|

Contact

Copyright © 2025 NVIDIA Corporation

google

deplot

PREVIEW

Translate images of plots into tables with one-shot visual language understanding.

multimodaldata ingestionnemo retrieverimage-to-text
Get API Key
API Reference
Accelerated by DGX Cloud

Model Overview

Description:

The Google DePlot model is a one-shot visual language understanding solution that translates images of plots or charts into linearized tables.

Terms of use

By using this model, you are agreeing to the terms and conditions of the license, acceptable use policy and Google Research privacy policy.

References(s):

  • DePlot paper
  • DePlot on HuggingFace

Model Architecture:

Architecture Type: Transformer
Network Architecture: Pix2Struct

Input:

Input Format: Red, Green, Blue (RGB) Image + Text
Input Parameters: None
Other Properties Related to Input: None

Output:

Output Format: Text
Output Parameters: temperature, top_p, max_tokens
Other Properties Related to Output: stream

Supported Operating System(s):

Linux

Inference:

Engine: Triton
Test Hardware: Other